Glossary term
Retrieval-augmented generation (RAG)
A pattern in which relevant passages are retrieved from a body of content and given to a language model to ground its answer.
RAG lets a model answer from current, private content without retraining. The quality of the answer depends mostly on whether the right passages are retrieved.
Good RAG systems carry access permissions into retrieval, cite their sources and abstain when evidence is weak.
Read more
Related terms
- EmbeddingA numerical vector representing the meaning of text, images or other data, so that similar items have nearby vectors.
- Vector databaseA data store optimised for finding the vectors most similar to a query vector, used for semantic search over embeddings.
- Hybrid searchCombining keyword-based and vector-based retrieval, then merging and re-ranking the results.
- GroundingConstraining a model’s output to information in supplied sources, so that claims can be traced and verified.
Turning concepts into a working system?
We help teams choose the right pattern and build it with evaluation from day one.